HN Morning Brief

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  1.0.1

Overview

This skill coherently fetches and summarizes Hacker News stories, with expected network use and memory-based personalization disclosed in the instructions.

Install this if you are comfortable with it running a small bundled Python script, fetching Hacker News RSS data, opening article URLs you ask about, and using saved interests to personalize ranking. No destructive behavior, credential use, hidden persistence, or unrelated data access was evident.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill instructs the agent to execute a Python script that fetches Hacker News stories and later to read arbitrary article URLs, which are network-capable behaviors, but no corresponding permission is declared. This creates a trust and sandboxing gap: operators and policy systems cannot accurately assess or constrain outbound network access, and the later 'dive deeper' flow may cause requests to untrusted third-party URLs from HN content.

VirusTotal

64/64 vendors flagged this skill as clean.